arXiv:2609.36864v1 Announce Type: new Abstract: Group-relative methods for reinforcement learning with verifiable rewards (RLVR) learn from differences in rollout outcomes. Independently sampling com...
arXiv:2607. 13389v1 Announce Type: new Abstract: Reinforcement Learning (RL) post-training is increasingly used to adapt foundation models for reasoning, planning, and feedback-driven robot-learning pipelines, but constrained post-training resources are often summarized by a single total FLOP budget.
arXiv:2610.00360v1 Announce Type: cross Abstract: Reinforcement learning (RL) for dexterous manipulation must discover finger-object contacts and then control the object precisely; the action noise t...
arXiv:2608. 00335v1 Announce Type: cross Abstract: Compact web agents can reduce deployment cost, but training them poses challenges in both data collection and post-SFT reinforcement learning (RL).
arXiv:2606. 19004v1 Announce Type: cross Abstract: Reinforcement learning (RL) post-training of Diffusion Transformers (DiTs) is prohibitively expensive, requiring thousands of high-end GPUs.
arXiv:2608. 03483v1 Announce Type: cross Abstract: Existing chunk-based Vision-Language-Action (VLA) models execute a fixed number of actions (i.
arXiv:2606. 16978v1 Announce Type: cross Abstract: For residual learning that refines existing behavior, sample efficiency depends on two things: how much information each rollout returns, and how efficiently the learner uses that information.
The paper introduces Bidirectional Voronoi-biased Exploration Curriculum (BVER), a method that expands start states from the goal and goals from the initial state simultaneously, guiding both toward each other to train a single goal-conditioned policy. Inspired by bidirectional RRT planning, BVER biases exploration toward unexplored task space and steers the two expansions together. Experiments on point-mass mazes, quadrupedal box climbing, and robot-arm ring-on-peg transfer show that BVER learns faster than other reference-free curricula, achieving high success rates and robustness without requiring demonstrations.
Computer-use agents learn from what their actions change, so training one needs applications it can act on, break and reset. The applications that matter most are login-gated and stateful, so synthetic environments stand in for them.
arXiv:2608.22533v1 Announce Type: new Abstract: Autonomous computer-use agents are increasingly applied to long-horizon tasks requiring coordinated application calls, persistent state tracking, and v...
arXiv:2609.13234v1 Announce Type: cross Abstract: Industrialized construction imposes stringent precision requirements on robotic assembly of modular components such as prefabricated window units. In...
The paper introduces T1, a 122‑billion‑parameter Mixture‑of‑Experts model trained with reinforcement learning to perform long‑horizon terminal tasks such as coding and scientific discovery. T1 operates a real shell in a cloud sandbox, making over 300 tool‑call turns per task and receiving rewards from task‑specific verifiers. The authors detail a training recipe that includes aggressive warm‑starting, TITO construction with drift repair, and rollout‑routing replay, achieving significant performance gains on Terminal‑Bench 2.1 and surpassing GPT‑5.4 and GLM‑5.1 on the Long‑Horizon Terminal Bench.